{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:3NSM5GFJSNDXG6MXM7LXPXCMHW","short_pith_number":"pith:3NSM5GFJ","schema_version":"1.0","canonical_sha256":"db64ce98a9934773799767d777dc4c3d90b679d4edd2d72440e9a987f3151352","source":{"kind":"arxiv","id":"1708.06734","version":1},"attestation_state":"computed","paper":{"title":"Representation Learning by Learning to Count","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hamed Pirsiavash, Mehdi Noroozi, Paolo Favaro","submitted_at":"2017-08-22T17:33:47Z","abstract_excerpt":"We introduce a novel method for representation learning that uses an artificial supervision signal based on counting visual primitives. This supervision signal is obtained from an equivariance relation, which does not require any manual annotation. We relate transformations of images to transformations of the representations. More specifically, we look for the representation that satisfies such relation rather than the transformations that match a given representation. In this paper, we use two image transformations in the context of counting: scaling and tiling. The first transformation explo"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1708.06734","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-22T17:33:47Z","cross_cats_sorted":[],"title_canon_sha256":"15513ad0d425251ff94f697e0c0c73a5312ac573c976d2315f7306f65e51ef39","abstract_canon_sha256":"5171803f285a14b80bcc7039d6150c58eb7c54dde3be2ab3af644e456d6e4504"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:37:32.783438Z","signature_b64":"+ULzYHYnfWX3KJ3BDhrCyWS2JmsBlsckDYo6AiiRwVG9byTCgyx6CIGRAe/fkMKaOGQqw1SpQB+iTqWGVtlnBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db64ce98a9934773799767d777dc4c3d90b679d4edd2d72440e9a987f3151352","last_reissued_at":"2026-05-18T00:37:32.782963Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:37:32.782963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Representation Learning by Learning to Count","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hamed Pirsiavash, Mehdi Noroozi, Paolo Favaro","submitted_at":"2017-08-22T17:33:47Z","abstract_excerpt":"We introduce a novel method for representation learning that uses an artificial supervision signal based on counting visual primitives. This supervision signal is obtained from an equivariance relation, which does not require any manual annotation. We relate transformations of images to transformations of the representations. More specifically, we look for the representation that satisfies such relation rather than the transformations that match a given representation. In this paper, we use two image transformations in the context of counting: scaling and tiling. The first transformation explo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.06734","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1708.06734","created_at":"2026-05-18T00:37:32.783042+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.06734v1","created_at":"2026-05-18T00:37:32.783042+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.06734","created_at":"2026-05-18T00:37:32.783042+00:00"},{"alias_kind":"pith_short_12","alias_value":"3NSM5GFJSNDX","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_16","alias_value":"3NSM5GFJSNDXG6MX","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_8","alias_value":"3NSM5GFJ","created_at":"2026-05-18T12:30:58.224056+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3NSM5GFJSNDXG6MXM7LXPXCMHW","json":"https://pith.science/pith/3NSM5GFJSNDXG6MXM7LXPXCMHW.json","graph_json":"https://pith.science/api/pith-number/3NSM5GFJSNDXG6MXM7LXPXCMHW/graph.json","events_json":"https://pith.science/api/pith-number/3NSM5GFJSNDXG6MXM7LXPXCMHW/events.json","paper":"https://pith.science/paper/3NSM5GFJ"},"agent_actions":{"view_html":"https://pith.science/pith/3NSM5GFJSNDXG6MXM7LXPXCMHW","download_json":"https://pith.science/pith/3NSM5GFJSNDXG6MXM7LXPXCMHW.json","view_paper":"https://pith.science/paper/3NSM5GFJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.06734&json=true","fetch_graph":"https://pith.science/api/pith-number/3NSM5GFJSNDXG6MXM7LXPXCMHW/graph.json","fetch_events":"https://pith.science/api/pith-number/3NSM5GFJSNDXG6MXM7LXPXCMHW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3NSM5GFJSNDXG6MXM7LXPXCMHW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3NSM5GFJSNDXG6MXM7LXPXCMHW/action/storage_attestation","attest_author":"https://pith.science/pith/3NSM5GFJSNDXG6MXM7LXPXCMHW/action/author_attestation","sign_citation":"https://pith.science/pith/3NSM5GFJSNDXG6MXM7LXPXCMHW/action/citation_signature","submit_replication":"https://pith.science/pith/3NSM5GFJSNDXG6MXM7LXPXCMHW/action/replication_record"}},"created_at":"2026-05-18T00:37:32.783042+00:00","updated_at":"2026-05-18T00:37:32.783042+00:00"}